Edge Detection and Ridge Detection with Automatic Scale Selection
International Journal of Computer Vision
Shape Constrained Deformable Models for 3D Medical Image Segmentation
IPMI '01 Proceedings of the 17th International Conference on Information Processing in Medical Imaging
Enhanced Artery Visualization in Blood Pool MRA: Results in the Peripheral Vasculature
IPMI '99 Proceedings of the 16th International Conference on Information Processing in Medical Imaging
Vascular Shape Segmentation and Structure Extraction Using a Shape-Based Region-Growing Model
MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
Muliscale Vessel Enhancement Filtering
MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
An Adaptive Minimal Path Generation Technique for Vessel Tracking in CTA/CE-MRA Volume Images
MICCAI '00 Proceedings of the Third International Conference on Medical Image Computing and Computer-Assisted Intervention
CVRMed-MRCAS '97 Proceedings of the First Joint Conference on Computer Vision, Virtual Reality and Robotics in Medicine and Medial Robotics and Computer-Assisted Surgery
A Real-Time Algorithm for Medical Shape Recovery
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Machine Graphics & Vision International Journal
A modification of the level set speed function to bridge gaps in data
DAGM'06 Proceedings of the 28th conference on Pattern Recognition
Scaffolding-based segmentation of coronary vascular structures
VG'05 Proceedings of the Fourth Eurographics / IEEE VGTC conference on Volume Graphics
| Hi-index | 0.00 |
We present a method for the segmentation of vessel structures in 3D magnetic resonance angiography (MRA) images with blood-pool contrast agent, allowing artery-vein separation for occluding vessel removal from MIP visualization. The method first uses a front propagation algorithm to select a path along the vessel of interest. Two controlling speed functions are considered, a multi-scale vessel filter, and an approach based on a cylinder shape model. The cylinder based method uses orientation information which is propagated with the front and iteratively updated as the surface expands. Once a vessel of interest is selected, orientation and radius parameters are used to construct a deformable model of the vessel, which is then adapted to the image borders to refine the segmentation of the selected vessel. The results of a comparison with manual segmentations are presented. The extracted centre lines are compared with those from the manual segmentations, showing a mean deviation of 2.55mm for the multi-scale filter, and 1.06mm for the cylinder model, compared to voxel dimensions of 0.93mm. The mean deviation of the final segmentation from the surface of the manual segmentation was 0.59mm.